dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 02:24:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21
3942 commits 62 branches 113 tags 38 MiB
Commit graph

3942 commits

This branch
This branch
All branches
Author SHA1 Message Date
Ettore Di Giacinto
6ce94834b6
fix(hipblas): do not build all cpu-specific flags (#5322) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-06 10:00:50 +02:00
dependabot[bot]
84a26458dc
chore(deps): bump mxschmitt/action-tmate from 3.21 to 3.22 (#5319) 
Bumps [mxschmitt/action-tmate](https://github.com/mxschmitt/action-tmate) from 3.21 to 3.22.
- [Release notes](https://github.com/mxschmitt/action-tmate/releases)
- [Changelog](https://github.com/mxschmitt/action-tmate/blob/master/RELEASE.md)
- [Commits](https://github.com/mxschmitt/action-tmate/compare/v3.21...v3.22)

---
updated-dependencies:
- dependency-name: mxschmitt/action-tmate
  dependency-version: '3.22'
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-05-05 22:17:59 +00:00
Ettore Di Giacinto
7aa377b6a9
fix(arm64): do not build instructions which are not available (#5318) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-05 17:30:00 +02:00
Ettore Di Giacinto
64e66dda4a
chore(model gallery): add allura-org_remnant-qwen3-8b (#5317) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-05 11:09:07 +02:00
LocalAI [bot]
a085f61fdc
chore: ⬆️ Update ggml-org/llama.cpp to 9fdfcdaeddd1ef57c6d041b89cd8fb7048a0f028 (#5316) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-05-04 23:00:25 +00:00
Ettore Di Giacinto
21bdfe5fa4
fix: use rice when embedding large binaries (#5309) 
* fix(embed): use go-rice for large backend assets

Golang embed FS has a hard limit that we might exceed when providing
many binary alternatives.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* simplify golang deps

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore(tests): switch to testcontainers and print logs

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(tests): do not build a test binary

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* small fixup

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-04 16:42:42 +02:00
Ettore Di Giacinto
7ebd7b2454
chore(model gallery): add rei-v3-kto-12b (#5313) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-04 09:41:35 +02:00
Ettore Di Giacinto
6984749ea1
chore(model gallery): add kalomaze_qwen3-16b-a3b (#5312) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-04 09:39:38 +02:00
Ettore Di Giacinto
c0a206bc7a
chore(model gallery): add qwen3-30b-a1.5b-high-speed (#5311) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-04 09:38:01 +02:00
LocalAI [bot]
01bbb31fb3
chore: ⬆️ Update ggml-org/llama.cpp to 36667c8edcded08063ed51c7d57e9e086bbfc903 (#5300) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-05-04 09:23:01 +02:00
Ettore Di Giacinto
72111c597d
fix(gpu): do not assume gpu being returned has node and mem (#5310) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-03 19:00:24 +02:00
Ettore Di Giacinto
b2f9fc870b
chore(defaults): enlarge defaults, drop gpu layers which is infered (#5308) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-03 18:44:51 +02:00
Ettore Di Giacinto
1fc6d469ac
chore(deps): bump llama.cpp to '1d36b3670b285e69e58b9d687c770a2a0a192194 (#5307) 
chore(deps): bump llama.cpp to '1d36b3670b285e69e58b9d687c770a2a0a192194'

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-03 18:44:40 +02:00
Ettore Di Giacinto
05848b2027
chore(model gallery): add smoothie-qwen3-8b (#5306) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-03 10:35:20 +02:00
Ettore Di Giacinto
1da0644aa3
chore(model gallery): add qwen-3-32b-medical-reasoning-i1 (#5305) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-03 10:24:07 +02:00
Ettore Di Giacinto
c087cd1377
chore(model gallery): add amoral-qwen3-14b (#5304) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-03 10:21:48 +02:00
Ettore Di Giacinto
c621412f6a
chore(model gallery): add comet_12b_v.5-i1 (#5303) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-03 10:20:03 +02:00
Ettore Di Giacinto
5a8b1892cd
chore(model gallery): add genericrpv3-4b (#5302) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-03 10:18:31 +02:00
Ettore Di Giacinto
5b20426863
chore(model gallery): add planetoid_27b_v.2 (#5301) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-03 10:14:33 +02:00
Ettore Di Giacinto
5c6cd50ed6
feat(llama.cpp): estimate vram usage (#5299) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-02 17:40:26 +02:00
Ettore Di Giacinto
bace6516f1
chore(model gallery): add webthinker-qwq-32b-i1 (#5298) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-02 09:57:49 +02:00
Ettore Di Giacinto
3baadf6f27
chore(model gallery): add shuttleai_shuttle-3.5 (#5297) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-02 09:48:11 +02:00
Ettore Di Giacinto
8804c701b8
chore(model gallery): add microsoft_phi-4-reasoning (#5296) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-02 09:46:20 +02:00
Ettore Di Giacinto
7b3ceb19bb
chore(model gallery): add microsoft_phi-4-reasoning-plus (#5295) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-02 09:43:38 +02:00
Ettore Di Giacinto
e7f3effea1
chore(model gallery): add furina-8b (#5294) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-02 09:39:22 +02:00
Ettore Di Giacinto
61694a2ffb
chore(model gallery): add josiefied-qwen3-8b-abliterated-v1 (#5293) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-02 09:36:35 +02:00
LocalAI [bot]
573a3f104c
chore: ⬆️ Update ggml-org/llama.cpp to d7a14c42a1883a34a6553cbfe30da1e1b84dfd6a (#5292) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-05-02 09:21:38 +02:00
Ettore Di Giacinto
0e8af53a5b chore: update quickstart 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-01 22:36:33 +02:00
Ettore Di Giacinto
960ffa808c
chore(model gallery): add microsoft_phi-4-mini-reasoning (#5288) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-01 10:17:58 +02:00
Ettore Di Giacinto
92719568e5
chore(model gallery): add fast-math-qwen3-14b (#5287) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-01 10:14:51 +02:00
Ettore Di Giacinto
163939af71
chore(model gallery): add qwen3-8b-jailbroken (#5286) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-01 10:13:01 +02:00
Ettore Di Giacinto
399f1241dc
chore(model gallery): add qwen3-30b-a3b-abliterated (#5285) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-05-01 10:07:42 +02:00
LocalAI [bot]
58c9ade2e8
chore: ⬆️ Update ggml-org/llama.cpp to 3e168bede4d27b35656ab8026015b87659ecbec2 (#5284) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-05-01 10:01:39 +02:00
Ettore Di Giacinto
6e1c93d84f
fix(ci): comment out vllm tests 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-05-01 10:01:22 +02:00
Wyatt Neal
4076ea0494
fix: vllm missing logprobs (#5279) 
* working to address missing items

referencing #3436, #2930 - if i could test it, this might show that the
output from the vllm backend is processed and returned to the user

Signed-off-by: Wyatt Neal <wyatt.neal+git@gmail.com>

* adding in vllm tests to test-extras

Signed-off-by: Wyatt Neal <wyatt.neal+git@gmail.com>

* adding in tests to pipeline for execution

Signed-off-by: Wyatt Neal <wyatt.neal+git@gmail.com>

* removing todo block, test via pipeline

Signed-off-by: Wyatt Neal <wyatt.neal+git@gmail.com>

---------

Signed-off-by: Wyatt Neal <wyatt.neal+git@gmail.com>
 2025-04-30 12:55:07 +00:00
Ettore Di Giacinto
26cbf77c0d
chore(model gallery): add mlabonne_qwen3-4b-abliterated (#5283) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-30 11:09:58 +02:00
Ettore Di Giacinto
640790d628
chore(model gallery): add mlabonne_qwen3-8b-abliterated (#5282) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-30 11:08:26 +02:00
Ettore Di Giacinto
4132adea2f
chore(model gallery): add mlabonne_qwen3-14b-abliterated (#5281) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-30 11:04:49 +02:00
LocalAI [bot]
2b2d907a3a
chore: ⬆️ Update ggml-org/llama.cpp to e2e1ddb93a01ce282e304431b37e60b3cddb6114 (#5278) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-04-29 21:46:08 +00:00
Ettore Di Giacinto
6e8f4f584b
fix(diffusers): consider options only in form of key/value (#5277) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-29 17:08:55 +02:00
Richard Palethorpe
662cfc2b48
fix(aio): Fix copypasta in download files for gpt-4 model (#5276) 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2025-04-29 17:08:16 +02:00
Ettore Di Giacinto
a25d355d66
chore(model gallery): add qwen3-0.6b (#5275) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-29 10:10:16 +02:00
Ettore Di Giacinto
6d1cfdbefc
chore(model gallery): add qwen3-1.7b (#5274) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-29 10:06:03 +02:00
Ettore Di Giacinto
5ecc478968
chore(model gallery): add qwen3-4b (#5273) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-29 10:01:22 +02:00
Ettore Di Giacinto
aef5c4291b
chore(model gallery): add qwen3-8b (#5272) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-29 09:59:17 +02:00
Ettore Di Giacinto
c059f912b9
chore(model gallery): add qwen3-14b (#5271) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-29 09:56:50 +02:00
LocalAI [bot]
bc1e059259
chore: ⬆️ Update ggml-org/llama.cpp to 5f5e39e1ba5dbea814e41f2a15e035d749a520bc (#5267) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-04-29 09:49:42 +02:00
LocalAI [bot]
38dc07793a
chore(model-gallery): ⬆️ update checksum (#5268) 
⬆️ Checksum updates in gallery/index.yaml

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-04-29 09:49:23 +02:00
Ettore Di Giacinto
da6ef0967d
chore(model gallery): add qwen3-32b (#5270) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-29 09:48:28 +02:00
Ettore Di Giacinto
7a011e60bd
chore(model gallery): add qwen3-30b-a3b (#5269) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-29 09:44:44 +02:00